registry / superclawd / 0.1.120
superclawd@0.1.120
Claude Code, supercharged — your team's standards, every session. The superclawd CLI loads your workspace's skills, agents, commands, workflows, and live directives into Claude Code as a plugin.
AI Security Review
scanned 9h ago · by lpm-firewall-aiThe reviewed runtime behavior matches the package's stated workspace and memory features. Session content is processed for AI-captured memories and sent to the SuperClawd service; the inspected paths showed no unrelated collection or malicious credential transport.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
The CLI registers capture hooks for session stop and end when memory is enabled and a repository fingerprint is available.
Impact
This supports the package's advertised cross-session memory feature; no unrelated credential collection or receiver was identified.
Mechanism
The helper processes conversation content into memory records and sends those records to the SuperClawd service using its configured credentials.
AI rationale
The reviewed runtime behavior matches the package's stated workspace and memory features. Session content is processed for AI-captured memories and sent to the SuperClawd service; the inspected paths showed no unrelated collection or malicious credential transport.
Network endpoints3
api.superclawd.commcp-api.superclawd.comregistry.npmjs.org
Decision evidence
public snapshotAI called this Clean at 94.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest identifies this as a Claude Code workspace CLI and points its main and bin entries to dist/index.js.
- The README describes repo and agent memories as AI-captured and says private memory is on by default with an option to turn it off.
- Session-end capture is gated by a repository fingerprint, memory settings, and the no-capture flag.
- The capture helper processes user and assistant conversation content to support memory generation.
- Memory records are submitted to the SuperClawd memory API using the configured service credentials.
Evidence against
Behavioral surface
ChildProcessEnvironmentVarsEvalFilesystemNetworkShell
HighEntropyStringsMinifiedUrlStrings
NoLicense
Source & flagged code
9 flaggeddist/index.jsView file
2Source sends the broad process environment to a literal external destination.
L2: import { createRequire as __cr } from 'module'; const require = __cr(import.meta.url);
L3: var Xe=["opus","fable","sonnet","haiku"],Un={opus:"claude-opus-5-5",fable:"claude-fable-5-1",sonnet:"claude-sonnet-5-5",haiku:"claude-haiku-5-5"},Wn=/^claude-(opus|fable|sonnet|hai...
L4: `,{mode:384});try{Bn(se,384)}catch{}}function nt(){return L()?.preferences?.sk[redacted]===!0}function qn(){return L()?.preferences?.notifications===!0}function rt(){return L()?...
L5: `)}catch{}}function ct(e,t,n=!1){et(lt(e))||Jn(e,{notifications:n?!1:qn(),...t?{workspace:t}:{}})}function ut(){et(se)||Y({credentials:{keyId:"",secret:"",workspace:""},preferences...
L6: `)};function Vn(){try{switch(process.platform){case"darwin":return
Critical
Hardcoded Runtime Data Exfiltration
Source sends credentials or rich application records to a package-controlled external receiver enabled by default.
dist/index.jsView on unpkg · L22import { createRequire as __cr } from 'module'; const require = __cr(import.meta.url);
L3: var Xe=["opus","fable","sonnet","haiku"],Un={opus:"claude-opus-5-5",fable:"claude-fable-5-1",sonnet:"claude-sonnet-5-5",haiku:"claude-haiku-5-5"},Wn=/^claude-(opus|fable|sonnet|hai...
L4: `,{mode:384});try{Bn(se,384)}catch{}}function nt(){return L()?.preferences?.sk[redacted]===!0}function qn(){return L()?.preferences?.notifications===!0}function rt(){return L()?...
High
Findings
1 Critical7 High3 Medium7 Low
CriticalHardcoded Runtime Data Exfiltrationdist/index.js
HighChild Processdist/index.js
HighShelldist/index.js
HighSame File Env Network Executiondist/index.js
HighCommand Output Exfiltrationdist/index.js
HighSandbox Evasion Gated Capabilitydist/index.js
HighTrigger Reachable Command Output Exfiltrationdist/index.js
HighSemantic Analysis Limiteddist/hook-helper.mjs#virtual:normalized:round1
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
Affected versions and remediation
This report applies to superclawd@0.1.120.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.120 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.